Note that MCP servers can implement multiple tools and as an agent developer you can decide which tools to use.
+Now let's try our agent out with the fetch tool.
-## Testing the agent with the MCP tool
+1. Open the kagent dashboard.
+
+ ```shell
+ kagent dashboard
+ ```
-Now let's try our agent out with the new integration. Open the kagent dashboard and select the agent we just created. You should see a new tool appear in the tool list.
+2. Select the **simple-fetch-agent** that you just created. Under **Agent Details**, you see the **fetch** tool.
-Now let's ask our agent a question. Type "Show me the contents of the https://en.wikipedia.org/wiki/Service_mesh website?" and press enter. The agent should respond with the contents of the website.
+3. In the chat box, enter `"Show me the contents of the https://en.wikipedia.org/wiki/Service_mesh website?"` and click **Send**. The agent responds with the contents of the website.
diff --git a/src/app/docs/kagent/getting-started/page.mdx b/src/app/docs/kagent/getting-started/page.mdx
index 844e378d..eaa8d382 100644
--- a/src/app/docs/kagent/getting-started/page.mdx
+++ b/src/app/docs/kagent/getting-started/page.mdx
@@ -10,6 +10,19 @@ export const metadata = {
author: "kagent.dev"
};
-# Getting Started
+import QuickLink from '@/components/quick-link';
-This section will guide you through the initial steps of using kagent.
\ No newline at end of file
+
+
+
Getting Started
+
Guides to help you get started with kagent, from quick setup to your first agent and tool.
+
+
+
+
+
+
+
+
+
+
+
+
Introduction
+
Welcome to kagent! Start here to understand what kagent is, how to install it, and how to contribute.
+
-Explore the following pages to get started:
-
-- **[What is kagent?](/docs/kagent/introduction/what-is-kagent)**: Learn about the core concepts and capabilities of kagent.
-- **[Installation](/docs/kagent/introduction/installation)**: Follow our guide to set up kagent.
-- **[Feature Roadmap](https://github.com/kagent-dev/kagent/blob/main/README.md#roadmap)**: See what we're planning for the future.
-- **[Contributing](https://github.com/kagent-dev/kagent/blob/main/CONTRIBUTION.md)**: Find out how you can help improve kagent.
\ No newline at end of file
+
+
+
+
+
+
+
+
+
Resources
+
Find helpful resources, troubleshooting tips, and FAQs for kagent. Access guides, community links, and more.
+
-## Helpful Links
-
-- [Troubleshooting Guide](/docs/kagent/resources/troubleshooting)
-- [Frequently Asked Questions](/docs/kagent/resources/faq)
-- [Quick Start Guide](/docs/kagent/getting-started/quickstart)
-- [Official GitHub Repository](https://github.com/kagent-dev/kagent)
-- [Contribution Guide](https://github.com/kagent-dev/kagent/blob/main/CONTRIBUTION.md)
-- [Join our Discord Community](https://discord.gg/Fu3k65f2k3)
\ No newline at end of file
+
+
+
+
+
+
+
+
+
Old ToolServer API:
```yaml
- apiVersion: kagent.dev/v1alpha1
+ apiVersion: kagent.dev/v1alpha2
kind: ToolServer
metadata:
name: kagent-tool-server
@@ -211,7 +219,7 @@ spec:
protocol: TCP
targetPort: http
---
-apiVersion: kagent.dev/v1alpha1
+apiVersion: kagent.dev/v1alpha2
kind: ToolServer
metadata:
name: kagent-querydoc
@@ -355,8 +363,8 @@ This change supports the new type for BYO agents.
namespace: kagent
spec:
description: An Kubernetes Expert AI Agent specializing in cluster operations, troubleshooting, and maintenance.
- type: Inline
- inline:
+ type: Declarative
+ declarative:
systemMessage: |
# Kubernetes AI Agent System Prompt
@@ -365,7 +373,7 @@ This change supports the new type for BYO agents.
```
**Key Changes:**
- * Added `type: Inline` field to specify agent type
+ * Added `type: Declarative` field to specify agent type
* Agent configuration now under `inline` section
* Supports new BYO deployment model
@@ -397,4 +405,8 @@ spec:
## ModelConfig API
-The secret name field is renamed from `apiKeySecretRef` to `apiKeySecret`.
+The secret name field is renamed from `apiKeySecret` to `apiKeySecret`.
+
+## Memory API
+
+The Memory API is not supported in ADK. The [agent development kit](https://google.github.io/adk-docs/) is required to bring your own agents. As such, the Memory docs are removed.
diff --git a/src/app/docs/kagent/supported-providers/anthropic/page.mdx b/src/app/docs/kagent/supported-providers/anthropic/page.mdx
index ba73dbcd..29176e0a 100644
--- a/src/app/docs/kagent/supported-providers/anthropic/page.mdx
+++ b/src/app/docs/kagent/supported-providers/anthropic/page.mdx
@@ -23,13 +23,13 @@ kubectl create secret generic kagent-anthropic -n kagent --from-literal ANTHROPI
2. Create a ModelConfig resource that references the secret and key name, and specify the Anthropic model you want to use:
```yaml
-apiVersion: kagent.dev/v1alpha1
+apiVersion: kagent.dev/v1alpha2
kind: ModelConfig
metadata:
name: claude-model-config
namespace: kagent
spec:
- apiKeySecretRef: kagent-anthropic
+ apiKeySecret: kagent-anthropic
apiKeySecretKey: ANTHROPIC_API_KEY
model: claude-3-sonnet-20240229
provider: Anthropic
diff --git a/src/app/docs/kagent/supported-providers/azure-openai/page.mdx b/src/app/docs/kagent/supported-providers/azure-openai/page.mdx
index d1b2ef6c..03cd1a42 100644
--- a/src/app/docs/kagent/supported-providers/azure-openai/page.mdx
+++ b/src/app/docs/kagent/supported-providers/azure-openai/page.mdx
@@ -22,13 +22,13 @@ kubectl create secret generic kagent-azureopenai -n kagent --from-literal AZURE_
2. Create a ModelConfig resource that references the secret and key name, and specify the additional information that's required for the Azure OpenAI - that's the deployment name, version and the Azure AD token. You can get these values from Azure.
```yaml
-apiVersion: kagent.dev/v1alpha1
+apiVersion: kagent.dev/v1alpha2
kind: ModelConfig
metadata:
- name: azureopenai-model-config
+ name: azuredefault-model-config
namespace: kagent
spec:
- apiKeySecretRef: kagent-azureopenai
+ apiKeySecret: kagent-azureopenai
apiKeySecretKey: AZURE_OPENAI_API_KEY
model: gpt-4o-mini
provider: AzureOpenAI
diff --git a/src/app/docs/kagent/supported-providers/custom-models/page.mdx b/src/app/docs/kagent/supported-providers/custom-models/page.mdx
index b129d48d..212d6607 100644
--- a/src/app/docs/kagent/supported-providers/custom-models/page.mdx
+++ b/src/app/docs/kagent/supported-providers/custom-models/page.mdx
@@ -102,13 +102,13 @@ kubectl create secret generic kagent-openai -n kagent --from-literal OPENAI_API_
2. Create a ModelConfig resource that references the secret and key name, and specify the model you want to use:
```yaml
-apiVersion: kagent.dev/v1alpha1
+apiVersion: kagent.dev/v1alpha2
kind: ModelConfig
metadata:
name: custom-openai-model-config
namespace: kagent
spec:
- apiKeySecretRef: kagent-openai
+ apiKeySecret: kagent-openai
apiKeySecretKey: OPENAI_API_KEY
model: # This should match the model name passed to the provider.
provider: OpenAI
@@ -124,7 +124,7 @@ spec:
multipleSystemMessages: false
```
-If you don't need an API key you can elide the `apiKeySecretRef` and `apiKeySecretKey` fields.
+If you don't need an API key you can elide the `apiKeySecret` and `apiKeySecretKey` fields.
3. Apply the above resource to the cluster.
diff --git a/src/app/docs/kagent/supported-providers/google-vertexai/page.mdx b/src/app/docs/kagent/supported-providers/google-vertexai/page.mdx
index b1d16a07..8fb06a4c 100644
--- a/src/app/docs/kagent/supported-providers/google-vertexai/page.mdx
+++ b/src/app/docs/kagent/supported-providers/google-vertexai/page.mdx
@@ -23,13 +23,13 @@ kubectl create secret generic kagent-google-creds -n kagent --from-file=./google
2. For Gemini models: create a ModelConfig resource using the `GeminiVertexAI` provider that references the secret and key name, and specify the Gemini model you want to use. Note the `projectID` and `location` are required:
```yaml
-apiVersion: kagent.dev/v1alpha1
+apiVersion: kagent.dev/v1alpha2
kind: ModelConfig
metadata:
name: gemini-model-config-vertexai
namespace: kagent
spec:
- apiKeySecretRef: kagent-google-creds
+ apiKeySecret: kagent-google-creds
apiKeySecretKey: google_creds.json
model: gemini-2.0-flash-lite
provider: GeminiVertexAI
@@ -42,13 +42,13 @@ spec:
3. For Anthropic models: create a ModelConfig resource using the `AnthropicVertexAI` provider that references the secret and key name, and specify the Anthropic model you want to use. Note the `projectID` and `location` are required:
```yaml
-apiVersion: kagent.dev/v1alpha1
+apiVersion: kagent.dev/v1alpha2
kind: ModelConfig
metadata:
name: anthropic-model-config-vertexai
namespace: kagent
spec:
- apiKeySecretRef: kagent-google-creds
+ apiKeySecret: kagent-google-creds
apiKeySecretKey: google_creds.json
model: claude-sonnet-4@20250514
provider: AnthropicVertexAI
diff --git a/src/app/docs/kagent/supported-providers/ollama/page.mdx b/src/app/docs/kagent/supported-providers/ollama/page.mdx
index d653fd6f..c0532f25 100644
--- a/src/app/docs/kagent/supported-providers/ollama/page.mdx
+++ b/src/app/docs/kagent/supported-providers/ollama/page.mdx
@@ -72,14 +72,14 @@ Once the pod has started, you can port-forward to the Ollama service and use `ol
Let's assume we've downloaded the `llama3` model, you can then use the following ModelConfig to configure the model:
```yaml
-apiVersion: kagent.dev/v1alpha1
+apiVersion: kagent.dev/v1alpha2
kind: ModelConfig
metadata:
name: llama3-model-config
namespace: kagent
spec:
apiKeySecretKey: OPENAI_API_KEY
- apiKeySecretRef: kagent-openai
+ apiKeySecret: kagent-openai
model: llama3
provider: Ollama
ollama:
diff --git a/src/app/docs/kagent/supported-providers/openai/page.mdx b/src/app/docs/kagent/supported-providers/openai/page.mdx
index aa4b0906..546a5358 100644
--- a/src/app/docs/kagent/supported-providers/openai/page.mdx
+++ b/src/app/docs/kagent/supported-providers/openai/page.mdx
@@ -22,13 +22,13 @@ kubectl create secret generic kagent-openai -n kagent --from-literal OPENAI_API_
2. Create a ModelConfig resource that references the secret and key name:
```yaml
-apiVersion: kagent.dev/v1alpha1
+apiVersion: kagent.dev/v1alpha2
kind: ModelConfig
metadata:
- name: openai-model-config
+ name: default-model-config
namespace: kagent
spec:
- apiKeySecretRef: kagent-openai
+ apiKeySecret: kagent-openai
apiKeySecretKey: OPENAI_API_KEY
model: gpt-4o-mini
provider: OpenAI
diff --git a/src/app/docs/kmcp/deploy/install-controller/page.mdx b/src/app/docs/kmcp/deploy/install-controller/page.mdx
index 48e4951b..5e9a0815 100644
--- a/src/app/docs/kmcp/deploy/install-controller/page.mdx
+++ b/src/app/docs/kmcp/deploy/install-controller/page.mdx
@@ -29,7 +29,15 @@ The kmcp controller manages the lifecycle of MCP servers that are defined in an
kind create cluster
```
-2. Install the following kmcp controller components in your cluster.
+2. Install the kmcp CRDs.
+
+ ```sh
+ helm install kmcp-crds oci://ghcr.io/kagent-dev/kmcp/helm/kmcp-crds \
+ --namespace kmcp-system \
+ --create-namespace
+ ```
+
+3. Install the following kmcp controller components in your cluster.
* The MCPServer Custom Resource Definition to define your MCP server.
* The ClusterRole and ClusterRoleBinding to control RBAC permissions for the kmcp controller.
* The kmcp controller deployment that automatically manages the lifecycle of MCPServer resources.
@@ -54,7 +62,7 @@ The kmcp controller manages the lifecycle of MCP servers that are defined in an
💡 View controller logs with: kubectl logs -l app.kubernetes.io/name=kmcp -n kmcp-system
```
-3. Verify that the kmcp controller manager is up and running.
+4. Verify that the kmcp controller manager is up and running.
```sh
kubectl get pods -n kmcp-system
```
@@ -65,7 +73,7 @@ The kmcp controller manages the lifecycle of MCP servers that are defined in an
kmcp-controller-manager-66c8764c66-8h5sl 1/1 Running 0 27h
```
-4. Optional: Look at the logs of the kmcp controller manager.
+5. Optional: Look at the logs of the kmcp controller manager.
```sh
kubectl logs -l app.kubernetes.io/name=kmcp -n kmcp-system
```
diff --git a/src/app/docs/kmcp/deploy/page.mdx b/src/app/docs/kmcp/deploy/page.mdx
index 3b43dc89..decde3c8 100644
--- a/src/app/docs/kmcp/deploy/page.mdx
+++ b/src/app/docs/kmcp/deploy/page.mdx
@@ -10,10 +10,16 @@ export const metadata = {
author: "kagent.dev"
};
-# Deploy to Kubernetes
+import QuickLink from '@/components/quick-link';
-Use the kmcp controller to manage the lifecycle of your MCP servers in a Kubernetes environment.
+
+
+
Deploy to Kubernetes
+
Use the kmcp controller to manage the lifecycle of your MCP servers in a Kubernetes environment.
+
-Explore the following guides to get started:
-* [Install the kmcp controller](/docs/kmcp/deploy/install-controller)
-* [Deploy MCP servers](/docs/kmcp/deploy/server)
+
+
+
+
+
+
Develop MCP servers
+
Use kmcp to quickly create and initialize an MCP project on your local machine. kmcp automatically generates all the necessary files and dependencies so that you can get started with developing your MCP server and tools.
+
+
+
+
+
diff --git a/src/app/docs/kmcp/quickstart/page.mdx b/src/app/docs/kmcp/quickstart/page.mdx
index 0452d084..49e8658f 100644
--- a/src/app/docs/kmcp/quickstart/page.mdx
+++ b/src/app/docs/kmcp/quickstart/page.mdx
@@ -86,7 +86,15 @@ With your first FastMCP Python server up and running, you can now deploy it to a
kind create cluster
```
-2. Install the following kmcp controller components in your cluster.
+2. Install the kmcp CRDs.
+
+ ```sh
+ helm install kmcp-crds oci://ghcr.io/kagent-dev/kmcp/helm/kmcp-crds \
+ --namespace kmcp-system \
+ --create-namespace
+ ```
+
+3. Install the following kmcp controller components in your cluster.
* The MCPServer Custom Resource Definition to define your MCP server.
* The ClusterRole and ClusterRoleBinding to control RBAC permissions for the kmcp controller.
* The kmcp controller deployment that automatically manages the lifecycle of MCPServer resources.
@@ -111,7 +119,7 @@ With your first FastMCP Python server up and running, you can now deploy it to a
💡 View controller logs with: kubectl logs -l app.kubernetes.io/name=kmcp -n kmcp-system
```
-3. Verify that the kmcp controller manager is up and running.
+4. Verify that the kmcp controller manager is up and running.
```sh
kubectl get pods -n kmcp-system
```
diff --git a/src/app/docs/kmcp/reference/page.mdx b/src/app/docs/kmcp/reference/page.mdx
index 66eac19e..191831d9 100644
--- a/src/app/docs/kmcp/reference/page.mdx
+++ b/src/app/docs/kmcp/reference/page.mdx
@@ -4,13 +4,21 @@ pageOrder: 100
description: ""
---
-# Reference
+import QuickLink from '@/components/quick-link';
-Review the KMCP commands:
-* [kmcp add-tool](/docs/kmcp/reference/kmcp-add-tool) to generate an MCP tool boilerplate that you can use as the base to create your own.
-* [kmcp build](/docs/kmcp/reference/kmcp-build) to build a Docker image for your MCP server.
-* [kmcp deploy](/docs/kmcp/reference/kmcp-deploy) to deploy your MCP server to a Kubernetes cluster.
-* [kmcp init](/docs/kmcp/reference/kmcp-init) to create a scaffold for your MCP server project.
-* [kmcp install](/docs/kmcp/reference/kmcp-install) to install the KMCP controller manager and all its dependencies.
-* [kmcp run](/docs/kmcp/reference/kmcp-run) to run an MCP server on your local machine.
-* [kmcp secrets](/docs/kmcp/reference/kmcp-secrets) to create Kubernetes secrets for the environment variables that you want to use in your MCP server.
\ No newline at end of file
+
+
+
Reference
+
Review the KMCP commands and learn how to use them effectively.
+
+
+
+
+
+
+
+
+
+
+
+